© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3531
    Prev
    Next
    INDEX
    Explanations

    sports car

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मिली
    0.43
    䡛
    0.38
    鑽
    0.38
    -------------
    0.36
    eka
    0.36
    間
    0.36
    ポスト
    0.35
    ූර්
    0.35
     Melton
    0.35
     kapac
    0.34
    POSITIVE LOGITS
     />
    0.43
     PBC
    0.39
    ophosph
    0.38
     rosto
    0.38
     leveling
    0.38
     rifle
    0.37
     জিতে
    0.37
     khen
    0.37
     restored
    0.37
    
    0.37
    Activations Density 0.087%

    No Known Activations